Papers › JOLT-SQL: Joint Loss Tuning of Text-to-SQL with Confusion-aware Noisy Schema Sampling

JOLT-SQL: Joint Loss Tuning of Text-to-SQL with Confusion-aware Noisy Schema Sampling

20 May 2025arXiv:2505.14305archive 2025-07-28

Jinwang Song, Hongying Zan, Kunli Zhang, Lingling Mu, Yingjie Han, Haobo Hua, Min Peng

Text-to-SQL, which maps natural language to SQL queries, has benefited greatly from recent advances in Large Language Models (LLMs). While LLMs offer various paradigms for this task, including prompting and supervised fine-tuning (SFT), SFT approaches still face challenges such as complex multi-stage pipelines and poor robustness to noisy schema information. To address these limitations, we present JOLT-SQL, a streamlined single-stage SFT framework that jointly optimizes schema linking and SQL generation via a unified loss. JOLT-SQL employs discriminative schema linking, enhanced by local bidirectional attention, alongside a confusion-aware noisy schema sampling strategy with selective attention to improve robustness under noisy schema conditions. Experiments on the Spider and BIRD benchmarks demonstrate that JOLT-SQL achieves state-of-the-art execution accuracy among comparable-size open-source models, while significantly improving both training and inference efficiency.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

The archive's official repository (songjw133/joint-loss-tuning-of-text-to-sql) was not harvested; the 18 samples below come from 1 repository the archive does not mark official.

Syntology 18 code samples harvested from 1 repository linked to this paper: 16 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 4 violated, 2 with no contract checked; 10 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 8 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: found in paper text by Syntology: 18 samples from 1 repository, 16 ran (6 with no instrument failure; 10 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

songjw133/joint-loss-tuning-of-text-to-sql officialmentioned in paperSyntology: not harvested report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

18 samples harvested: 16 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 4 violated, 2 with no contract checked; 10 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

4ran · violated contract
8ran · our draft was wrong
2ran; the contract check could not run
2ran
2unverified

Licence: 1 of the 18 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from Songjw133/JOLT-SQL. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

Songjw133/JOLT-SQL found in paper text by Syntology 18 samples, 16 ran (10 instrument-failed) · 2 unverified
acc in 48 papers
census: 5 implementations from 5 papers, 2 distinct outputs across 2 buckets, one shared input per bucket
test_suite_sql_eval/evaluate_classical.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed Apache-2.0 (permissive) · bd001f76894a9867 · report fixture: signature l:list/1/bool, idxes:list/1/int · returned float · level recorded 2026-09-22
condition_has_like in 15 papers test_suite_sql_eval/evaluation.py ran · violated contract Apache-2.0 (permissive) · 8231e3fdffa9c8ee · report fixture: signature conds:list/1/tuple · returned bool · level recorded 2026-09-22
condition_has_or in 15 papers test_suite_sql_eval/evaluation.py ran · violated contract fingerprinted Apache-2.0 (permissive) · f2d76234528d3b57 · report fixture: signature conds:list/1/str · returned bool · level recorded 2026-09-22
condition_has_sql in 12 papers test_suite_sql_eval/evaluation.py ran · violated contract Apache-2.0 (permissive) · 954c76e256cc7220 · report fixture: signature conds:list/1/list · returned bool · level recorded 2026-09-22
find_subsequence JOLT_spider_v1.py ran fingerprinted Apache-2.0 (permissive) · 0e73074433136ad3 · report fixture: signature main_list:list/1/int, sub_list:list/1/int · returned int · level recorded 2026-09-25
get_cursor_from_path test_suite_sql_eval/exec_subprocess.py ran · our draft was wrong Apache-2.0 (permissive) · 2f701949fb88a0d5 · report fixture: signature sqlite_path:str/0/str · returned Cursor · level recorded 2026-09-22
get_schema in 16 papers test_suite_sql_eval/process_sql.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 0992d2a47ae733fa · report fixture: signature db:str/0/str · returned dict · level recorded 2026-09-24
get_schema_from_json in 14 papers test_suite_sql_eval/process_sql.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · c4dcaf29b663a364 · report fixture: signature fpath:str/0/str · returned dict · level recorded 2026-09-24
join_tokens in 7 papers test_suite_sql_eval/parse.py ran · our draft was wrong Apache-2.0 (permissive) · 2178b95c919ae420 · report fixture: signature tokens:list/1/Token · returned str · level recorded 2026-09-24
load_predictions in 22 papers test_suite_sql_eval/evaluate_classical.py ran · our draft was wrong Apache-2.0 (permissive) · c64a2627f38e10a8 · report fixture: signature f_path:str/0/str · returned list · level recorded 2026-09-22
permute_tuple in 7 papers test_suite_sql_eval/exec_eval.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · f23d6ff3772963bc · report fixture: signature element:tuple/1/int, perm:tuple/1/int · returned tuple · level recorded 2026-09-24
postprocess in 70 papers
census: 5 implementations from 5 papers, 5 distinct outputs across 2 buckets, one shared input per bucket
test_suite_sql_eval/parse.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 58e472cff9780d63 · report fixture: signature query:str/0/str · returned str · level recorded 2026-09-24
quick_rej in 7 papers test_suite_sql_eval/exec_eval.py ran · violated contract Apache-2.0 (permissive) · a40510ba6a37f798 · report fixture: signature result1:list/1/tuple, result2:list/1/tuple, order_matters:bool/0/bool · returned bool · level recorded 2026-09-24
replace_cur_year test_suite_sql_eval/exec_subprocess.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · d7bcb03a0faa63ed · report fixture: signature query:str/0/str · returned str · level recorded 2026-09-22
save_pristine_base_model_state utils.py ran Apache-2.0 (permissive) · a79a9b45387beff9 · report fixture: signature model:callable/0/? · returned dict · level recorded 2026-09-25
unorder_row in 7 papers test_suite_sql_eval/exec_eval.py ran · our draft was wrong Apache-2.0 (permissive) · afc8ef89576ef2aa · report fixture: signature row:tuple/1/str · returned tuple · level recorded 2026-09-24
getDataLoader in 6 papers JOLT_spider_v1.py unverified Apache-2.0 (permissive) · 3426fdab59498b56 · report
tokenize in 176 papers test_suite_sql_eval/process_sql.py unverified Apache-2.0 (permissive) · a906f5de1f5971b0 · report

Tasks

Text to SQLText-To-SQL

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AttentionSFTSoftmax

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections